GLM-4.7-REAP-40p

zai-org/GLM-4.7 (358B, 668GB BF16)
    ↓ REAP Pruning (40%)
GLM-4.7-REAP-40p (218B, 407GB)
    ↓ AutoRound W4A16
GLM-4.7-REAP-40p-W4A16-AutoRound (108GB) ← Recommended for inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "0xSero/GLM-4.7-REAP-40p"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Write a Python function to check if a number is prime."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))